© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97755
    Prev
    Next
    INDEX
    Explanations

    make a difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ventilación
    -1.10
     fisuras
    -1.09
     gebouw
    -1.04
     colocación
    -1.02
     dirigeants
    -1.02
     respiración
    -1.00
     voitures
    -0.97
     bañera
    -0.96
     cuarzo
    -0.95
     صحيح
    -0.94
    POSITIVE LOGITS
     in
    1.91
     to
    1.34
     difference
    1.23
     whether
    1.08
     outcome
    1.06
    difference
    1.04
     maker
    1.03
     outcomes
    1.02
    Whether
    1.01
     for
    0.99
    Activations Density 0.011%

    No Known Activations